import sklearn
import pandas
import seaborn 
import matplotlib.pyplot as plt
print("scikit-learn version:", sklearn.__version__)     # 1.1.3
print("pandas version:", pandas.__version__)            # 1.5.1
print("seaborn version:", seaborn.__version__)          # 0.12.1

scikit-learn version: 1.3.0
pandas version: 2.1.0
seaborn version: 0.12.2

import warnings
warnings.filterwarnings('ignore')

df = pandas.read_csv("Diamonds Prices2022.csv")
df

df.describe()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 53943 entries, 0 to 53942
Data columns (total 10 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   carat    53943 non-null  float64
 1   cut      53943 non-null  object 
 2   color    53943 non-null  object 
 3   clarity  53943 non-null  object 
 4   depth    53943 non-null  float64
 5   table    53943 non-null  float64
 6   price    53943 non-null  int64  
 7   x        53943 non-null  float64
 8   y        53943 non-null  float64
 9   z        53943 non-null  float64
dtypes: float64(6), int64(1), object(3)
memory usage: 4.1+ MB

# Define the binwidths
binwidths = [300, 5000, 7000]

plt.figure(figsize=(14, 4))

for i, binwidth in enumerate(binwidths, 1):
    plt.subplot(1, 3, i)
    plt.hist(df['price'], bins=range(0, df['price'].max() + binwidth, binwidth), color='gold', edgecolor='black')
    plt.xlabel('Price')
    plt.ylabel('Frequency')
    plt.title(f'Histogram of Price (Binwidth: {binwidth})')

plt.tight_layout()
plt.show()

# Create a figure with two subplots side by side
plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['depth'], bins=100, color='deepskyblue', edgecolor='black')
plt.xlabel('Depth')
plt.ylabel('Frequency')
plt.title('Histogram of Depth of Diamonds')

# Zoomed-in Distribution Plot
plt.subplot(1, 2, 2)
seaborn.histplot(df['depth'], bins=100, color='deepskyblue', edgecolor='black')
plt.xlabel('Depth')
plt.ylabel('Frequency')
plt.title('Zoomed-in Histogram of Depth of Diamonds')
plt.ylim(0, 40)  # Setting the y-axis limit for the zoomed-in plot

plt.tight_layout()  # Ensures proper spacing between subplots
plt.show()

plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['table'], bins=100, color='lightpink', edgecolor='black')
plt.xlabel('table')
plt.ylabel('Frequency')
plt.title('Histogram of table of Diamonds')

plt.subplot(1, 2, 2)
seaborn.histplot(df['table'], bins=100, color='lightpink', edgecolor='black')
plt.xlabel('table')
plt.ylabel('Frequency')
plt.title('Histogram of table of Diamonds')
plt.ylim(0, 40)
plt.tight_layout() 

plt.show()

plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['carat'], bins=100, color='teal', edgecolor='black')
plt.xlabel('Carat')
plt.ylabel('Frequency')
plt.title('Histogram of Carat of Diamonds')

plt.subplot(1, 2, 2)
seaborn.histplot(df['carat'], bins=100, color='teal', edgecolor='black')
plt.xlabel('Carat')
plt.ylabel('Frequency')
plt.title('Histogram of Carat of Diamonds')
plt.ylim(0, 40)   
plt.tight_layout() 


plt.show()

plt.figure(figsize=(8, 6))
smaller_diamonds = df[df['carat'] < 3]
seaborn.histplot(smaller_diamonds['carat'], bins=75, color='teal', edgecolor='black')
plt.xlabel('Carat')
plt.ylabel('Frequency')
plt.title('Histogram of Carat for Smaller Diamonds')
plt.show()

# Count the number of diamonds with carat value 0.99 and 1
count_099_carat = len(df[df['carat'] == 0.99])
count_1_carat = len(df[df['carat'] == 1])

print(f'Number of diamonds with 0.99 carat: {count_099_carat}')
print(f'Number of diamonds with 1 carat: {count_1_carat}')

Number of diamonds with 0.99 carat: 23
Number of diamonds with 1 carat: 1558

plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['y'], bins=100, color='limegreen', edgecolor='black')
plt.xlabel('Dimension y')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension y of Diamonds')

plt.subplot(1, 2, 2)
seaborn.histplot(df['y'], bins=100, color='limegreen', edgecolor='black')
plt.xlabel('Dimension y')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension y of Diamonds')
plt.ylim(0, 100)  
plt.tight_layout() 
plt.show()

plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['x'], bins=100, color='deepskyblue', edgecolor='black')
plt.xlabel('Dimension x')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension x of Diamonds')

plt.subplot(1, 2, 2)
seaborn.histplot(df['x'], bins=100, color='deepskyblue', edgecolor='black')
plt.xlabel('Dimension x')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension x of Diamonds')
plt.ylim(0, 100)   
plt.tight_layout() 
plt.show()

plt.figure(figsize=(16, 6))

plt.subplot(1, 2, 1)
seaborn.histplot(df['z'], bins=100, color='darkorange', edgecolor='black')
plt.xlabel('Dimension z')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension z of Diamonds')

plt.subplot(1, 2, 2)
seaborn.histplot(df['z'], bins=100, color='darkorange', edgecolor='black')
plt.xlabel('Dimension z')
plt.ylabel('Frequency')
plt.title('Histogram of Dimension z of Diamonds')
plt.ylim(0, 100)  # Set the y-axis limits 
plt.tight_layout() 
plt.show()

# Set up subplots
fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(18, 6))

# Distribution of Cut
seaborn.countplot(data=df, x='cut', palette='Set1', ax=axes[0])
axes[0].set_title('Distribution of Cut')
axes[0].set_xlabel('Cut')
axes[0].set_ylabel('Count')

# Distribution of Color
seaborn.countplot(data=df, x='color', palette='Set2', ax=axes[1])
axes[1].set_title('Distribution of Color')
axes[1].set_xlabel('Color')
axes[1].set_ylabel('Count')

# Distribution of Clarity
seaborn.countplot(data=df, x='clarity', palette='Set3', ax=axes[2])
axes[2].set_title('Distribution of Clarity')
axes[2].set_xlabel('Clarity')
axes[2].set_ylabel('Count')

plt.tight_layout()
plt.show()

# Numerical features vs. Price (Scatter plots)
plt.figure(figsize=(18, 12))

plt.subplot(2, 3, 1)
seaborn.scatterplot(x='carat', y='price', data=df, color='blue', alpha=0.5)
plt.title('Carat vs. Price')

plt.subplot(2, 3, 2)
seaborn.scatterplot(x='depth', y='price', data=df, color='green', alpha=0.5)
plt.title('Depth vs. Price')

plt.subplot(2, 3, 3)
seaborn.scatterplot(x='table', y='price', data=df, color='orange', alpha=0.5)
plt.title('Table vs. Price')

plt.subplot(2, 3, 4)
seaborn.scatterplot(x='x', y='price', data=df, color='red', alpha=0.5)
plt.title('X vs. Price')

plt.subplot(2, 3, 5)
seaborn.scatterplot(x='y', y='price', data=df, color='purple', alpha=0.5)
plt.title('Y vs. Price')

plt.subplot(2, 3, 6)
seaborn.scatterplot(x='z', y='price', data=df, color='brown', alpha=0.5)
plt.title('Z vs. Price')

plt.tight_layout()
plt.show()

plt.figure(figsize=(10, 6))
plt.scatter(df['carat'], df['price'], color='blue', alpha=0.3)
plt.xlabel('Carat')
plt.ylabel('Price')
plt.title('Scatter Plot of Carat vs Price')
plt.show()

sampled_data = df.sample(n=5000)  
plt.scatter(sampled_data['carat'], sampled_data['price'], color='blue', alpha=0.3)

<matplotlib.collections.PathCollection at 0x1ed477f5b90>

# Categorical features vs. Price (Box plots)
plt.figure(figsize=(18, 6))

plt.subplot(1, 3, 1)
seaborn.boxplot(x='cut', y='price', data=df, palette='Set1')
plt.title('Cut vs. Price')

plt.subplot(1, 3, 2)
seaborn.boxplot(x='color', y='price', data=df, palette='Set1')
plt.title('Color vs. Price')

plt.subplot(1, 3, 3)
seaborn.boxplot(x='clarity', y='price', data=df, palette='Set1')
plt.title('Clarity vs. Price')

plt.tight_layout()
plt.show()

df.sample(10)

#verify if the dataset has na values
df.isna().sum()

carat      0
cut        0
color      0
clarity    0
depth      0
table      0
price      0
x          0
y          0
z          0
dtype: int64

sum_zero_x = df.loc[df['x'] == 0, 'x'].count()
sum_zero_y = df.loc[df['y'] == 0, 'y'].count()
sum_zero_z = df.loc[df['z'] == 0, 'z'].count()

print("count of elements equal to zero in x:", sum_zero_x)
print("count of elements equal to zero in y:", sum_zero_y)
print("count  of elements equal to zero in z:", sum_zero_z)

count of elements equal to zero in x: 8
count of elements equal to zero in y: 7
count  of elements equal to zero in z: 20

#Dropping dimentionless diamonds
df = df.drop(df[df["x"]==0].index)
df = df.drop(df[df["y"]==0].index)
df = df.drop(df[df["z"]==0].index)

#Dropping the outliers. 
df = df[(df["depth"]<75)&(df["depth"]>45)]
df = df[(df["table"]<80)&(df["table"]>40)]
df = df[(df["x"]<30)]
df = df[(df["y"]<30)]
df = df[(df["z"]<30)&(df["z"]>2)]

unique1=df["cut"].unique()
unique2=df["color"].unique()
unique3=df["clarity"].unique()

unique1

array(['Ideal', 'Premium', 'Good', 'Very Good', 'Fair'], dtype=object)

unique2

array(['E', 'I', 'J', 'H', 'F', 'G', 'D'], dtype=object)

unique3

array(['SI2', 'SI1', 'VS1', 'VS2', 'VVS2', 'VVS1', 'I1', 'IF'],
      dtype=object)

# Define a custom mapping dictionary based on ranking values
cut_mapping = {
    'Fair': 4,  # Least Preferred
    'Good': 3,
    'Very Good': 2,
    'Premium': 1,
    'Ideal': 0  # Most Preferred
}

# Apply the custom mapping to the 'cut' column
df['cut'] = df['cut'].map(cut_mapping)

# Define a custom mapping dictionary based on ranking values
clarity_mapping = {
    'I1': 7,  # Least Preferred
    'SI2': 6,
    'SI1': 5,
    'VS2': 4,
    'VS1': 3,
    'VVS2': 2,
    'VVS1': 1,
    'IF': 0  # Most Preferred
}

# Apply the custom mapping to the 'clarity' column
df['clarity'] = df['clarity'].map(clarity_mapping)

# Define a custom mapping dictionary based on ranking values
color_mapping = {
    'J': 6,  # Least Preferred
    'I': 5,
    'H': 4,
    'G': 3,
    'F': 2,
    'E': 1,
    'D': 0  # Most Preferred
}

# Apply the custom mapping to the 'color' column
df['color'] = df['color'].map(color_mapping)

df

correlations = df.corr()
plot = seaborn.heatmap(correlations, cbar=True, annot=True, fmt=".1f", vmin=-1)

features= ['depth', 'clarity','cut','table','color','x', 'y', 'z','carat']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=42)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.linear_model import LinearRegression
model = LinearRegression()
result = model.fit(X_train, y_train)
score = model.score(X_test, y_test)
print("R²:", score)

R²: 0.9087616369934168

predictions = model.predict(X_test)

prediction_overview = pandas.DataFrame()
prediction_overview["truth"] = y_test
prediction_overview["prediction"] = predictions
prediction_overview["difference"] = prediction_overview["truth"] - prediction_overview["prediction"]
prediction_overview["difference"] = abs(prediction_overview["difference"].astype(int))
prediction_overview = prediction_overview.reset_index(drop=True)
prediction_overview

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 22945
Root Mean Squared difference: 1192

plot = seaborn.regplot(y=y_test.values.flatten(), x=predictions.flatten(), line_kws={"color": "r"})
plot.set_xlabel("predicted diamond price")
plot.set_ylabel("true diamond price")
plot

<Axes: xlabel='predicted diamond price', ylabel='true diamond price'>

plot = seaborn.residplot(y=y_test,x=predictions)
plot.set_xlabel('Predicted Values')
plot.set_ylabel('Residuals')
plot.set_title('Residual Plot')
plot

<Axes: title={'center': 'Residual Plot'}, xlabel='Predicted Values', ylabel='Residuals'>

features= [ 'clarity','cut','color','carat']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=42)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.linear_model import LinearRegression
model = LinearRegression()
result = model.fit(X_train, y_train)
score = model.score(X_test, y_test)
print("R²:", score)

R²: 0.9048849423757335

predictions = model.predict(X_test)

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 19805
Root Mean Squared difference: 1217

plot = seaborn.regplot(y=y_test.values.flatten(), x=predictions.flatten(), line_kws={"color": "r"})
plot.set_xlabel("predicted diamond price")
plot.set_ylabel("true diamond price")
plot

<Axes: xlabel='predicted diamond price', ylabel='true diamond price'>

plot = seaborn.residplot(y=y_test,x=predictions)
plot.set_xlabel('Predicted Values')
plot.set_ylabel('Residuals')
plot.set_title('Residual Plot')
plot

<Axes: title={'center': 'Residual Plot'}, xlabel='Predicted Values', ylabel='Residuals'>

features= ['x', 'y', 'z']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=42)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.linear_model import LinearRegression
model = LinearRegression()
result = model.fit(X_train, y_train)
score = model.score(X_test, y_test)
print("R²:", score)

R²: 0.7885621800622987

predictions = model.predict(X_test)

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 12155
Root Mean Squared difference: 1814

plot = seaborn.regplot(y=y_test.values.flatten(), x=predictions.flatten(), line_kws={"color": "r"})
plot.set_xlabel("predicted diamond price")
plot.set_ylabel("true diamond price")
plot

<Axes: xlabel='predicted diamond price', ylabel='true diamond price'>

plot = seaborn.residplot(y=y_test,x=predictions)
plot.set_xlabel('Predicted Values')
plot.set_ylabel('Residuals')
plot.set_title('Residual Plot')
plot

<Axes: title={'center': 'Residual Plot'}, xlabel='Predicted Values', ylabel='Residuals'>

features= ['depth','table']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=42)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.linear_model import LinearRegression
model = LinearRegression()
result = model.fit(X_train, y_train)
score = model.score(X_test, y_test)
print("R²:", score)

R²: 0.017558648525327736

predictions = model.predict(X_test)

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 15395
Root Mean Squared difference: 3909

plot = seaborn.regplot(y=y_test.values.flatten(), x=predictions.flatten(), line_kws={"color": "r"})
plot.set_xlabel("predicted diamond price")
plot.set_ylabel("true diamond price")
plot

<Axes: xlabel='predicted diamond price', ylabel='true diamond price'>

plot = seaborn.residplot(y=y_test,x=predictions)
plot.set_xlabel('Predicted Values')
plot.set_ylabel('Residuals')
plot.set_title('Residual Plot')
plot

<Axes: title={'center': 'Residual Plot'}, xlabel='Predicted Values', ylabel='Residuals'>

features= ['x', 'y', 'z','carat']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2,random_state=42)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.linear_model import LinearRegression
model = LinearRegression()
result = model.fit(X_train, y_train)
score = model.score(X_test, y_test)
print("R²:", score)

R²: 0.8583639522566571

predictions = model.predict(X_test)

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 23580
Root Mean Squared difference: 1485

plot = seaborn.regplot(y=y_test.values.flatten(), x=predictions.flatten(), line_kws={"color": "r"})
plot.set_xlabel("predicted diamond price")
plot.set_ylabel("true diamond price")
plot

<Axes: xlabel='predicted diamond price', ylabel='true diamond price'>

plot = seaborn.residplot(y=y_test,x=predictions)
plot.set_xlabel('Predicted Values')
plot.set_ylabel('Residuals')
plot.set_title('Residual Plot')
plot

<Axes: title={'center': 'Residual Plot'}, xlabel='Predicted Values', ylabel='Residuals'>

from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import plot_tree

# Features and target
features = ['clarity', 'color', 'y','z','x','depth','table']
target = 'price'

X = df[features]
y = df[target]

# Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Decision Tree for feature importance
decision_tree = DecisionTreeRegressor(random_state=42)
decision_tree.fit(X_train, y_train)

DecisionTreeRegressor(random_state=42)

DecisionTreeRegressor(random_state=42)

plt.figure(figsize=(15, 6))
plot = seaborn.barplot(y=decision_tree.feature_importances_, x=features)

# Visualize the Decision Tree
plt.figure(figsize=(30, 20))
plot_tree(decision_tree, feature_names=features,fontsize=7, filled=True,max_depth=4)
plt.show()

features= ['clarity','color','y']
target= "price"

X = df[features]
y = df[target]

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
print("There are in total", len(X), "observations, of which", len(X_train), "are now in the train set, and", len(X_test), "in the test set.")

There are in total 53910 observations, of which 43128 are now in the train set, and 10782 in the test set.

from sklearn.ensemble import RandomForestRegressor
random_forest = RandomForestRegressor( n_jobs=-1, random_state=42)
random_forest.fit(X_train, y_train)
predictions_random = random_forest.predict(X_test)
R_square=random_forest.score(X_test, y_test)
print("R-squared score:", R_square)

R-squared score: 0.9691172480215086

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions_random)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions_random)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 6650
Root Mean Squared difference: 695

from sklearn.model_selection import GridSearchCV

param_grid = {
    'min_samples_split': [2, 5, 10,15],
    'min_samples_leaf': [1, 2, 4,6],
    'bootstrap': [True, False]
}

random_forest = RandomForestRegressor(random_state=42) 
grid_search = GridSearchCV(random_forest, param_grid, cv=5, scoring='r2')
grid_search.fit(X_train, y_train)

# Get the best hyperparameters
best_params = grid_search.best_params_
print("Best Hyperparameters:", best_params)

Best Hyperparameters: {'bootstrap': True, 'min_samples_leaf': 6, 'min_samples_split': 15}

from sklearn.ensemble import RandomForestRegressor

optimized_random_forest = RandomForestRegressor(bootstrap= True,  min_samples_leaf= 6, min_samples_split= 15, n_jobs=-1, random_state=42)
optimized_random_forest.fit(X_train, y_train)
predictions_optimized = optimized_random_forest.predict(X_test)
optimized_R_square=optimized_random_forest.score(X_test, y_test)
print("R-squared score:", optimized_R_square)

R-squared score: 0.9739439995303263

from sklearn.model_selection import  cross_val_score

# Cross-validation
cv_scores = cross_val_score(optimized_random_forest, X_train, y_train, cv=5, scoring='r2')
print("Cross-Validation Scores:", cv_scores)
print("Mean R-squared Score:", cv_scores.mean())

Cross-Validation Scores: [0.97605937 0.97619518 0.9749442  0.97481567 0.97546035]
Mean R-squared Score: 0.9754949558805827

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions_optimized)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions_optimized)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 6198
Root Mean Squared difference: 639

import matplotlib.pyplot as plt

# Scatter plot
plt.scatter(y_test, predictions_optimized, alpha=0.5)
plt.title('Actual Prices vs Predicted Prices')
plt.xlabel('Actual Prices')
plt.ylabel('Predicted Prices')
plt.show()

from sklearn.ensemble import AdaBoostRegressor

# optimized random forest as the base model
base_model = optimized_random_forest

boosted_model = AdaBoostRegressor(base_model, learning_rate=0.1, random_state=42)

boosted_model.fit(X_train, y_train)

# Predictions
predictions_boosted = boosted_model.predict(X_test)

# Evaluate the model
score_boosted = boosted_model.score(X_test, y_test)
print("Boosted Random Forest Model R-squared score:", score_boosted)

Boosted Random Forest Model R-squared score: 0.9726271244653908

import io, math
from sklearn.metrics import max_error
from sklearn.metrics import mean_squared_error

me = max_error(y_test, predictions_boosted)
me = math.ceil(me)
print("Max difference:", me)

mse = mean_squared_error(y_test, predictions_boosted)
rmse = math.sqrt(mse)
rmse = math.ceil(rmse)
print("Root Mean Squared difference:", rmse)

Max difference: 6467
Root Mean Squared difference: 655

import pandas as pd

model = optimized_random_forest

def predict_diamond_price():
    try:
        clarity = float(input("Enter clarity (0-7): "))
        color = float(input("Enter color (0-6): "))
        y = float(input("Enter Y dimension (3.68-10.54): "))

        if 0 <= clarity <= 7 and 0 <= color <= 6 and 3.68 <= y <= 10.54:
            input_data = pd.DataFrame({"clarity": [clarity], "color": [color], "y": [y]})
            price_prediction = model.predict(input_data)[0]
            error_margin_percentage = 1

            # Calculate error margin
            error_margin = price_prediction * (error_margin_percentage / 100)

            # Calculate price range
            lower_bound = price_prediction - error_margin
            upper_bound = price_prediction + error_margin

            print(f"Predicted Diamond Price Range: {lower_bound:.2f} to {upper_bound:.2f}")
        else:
            print("Invalid input. Please enter values within the specified ranges.")
 
    except ValueError:
        print("Invalid input. Please enter numeric values.")

predict_diamond_price()

Predicted Diamond Price Range: 1040.04 to 1061.05

	carat	cut	color	clarity	depth	table	price	x	y	z
0	0.23	Ideal	E	SI2	61.5	55.0	326	3.95	3.98	2.43
1	0.21	Premium	E	SI1	59.8	61.0	326	3.89	3.84	2.31
2	0.23	Good	E	VS1	56.9	65.0	327	4.05	4.07	2.31
3	0.29	Premium	I	VS2	62.4	58.0	334	4.20	4.23	2.63
4	0.31	Good	J	SI2	63.3	58.0	335	4.34	4.35	2.75
...	...	...	...	...	...	...	...	...	...	...
53938	0.86	Premium	H	SI2	61.0	58.0	2757	6.15	6.12	3.74
53939	0.75	Ideal	D	SI2	62.2	55.0	2757	5.83	5.87	3.64
53940	0.71	Premium	E	SI1	60.5	55.0	2756	5.79	5.74	3.49
53941	0.71	Premium	F	SI1	59.8	62.0	2756	5.74	5.73	3.43
53942	0.70	Very Good	E	VS2	60.5	59.0	2757	5.71	5.76	3.47

	carat	depth	table	price	x	y	z
count	53943.000000	53943.000000	53943.000000	53943.000000	53943.000000	53943.000000	53943.000000
mean	0.797935	61.749322	57.457251	3932.734294	5.731158	5.734526	3.538730
std	0.473999	1.432626	2.234549	3989.338447	1.121730	1.142103	0.705679
min	0.200000	43.000000	43.000000	326.000000	0.000000	0.000000	0.000000
25%	0.400000	61.000000	56.000000	950.000000	4.710000	4.720000	2.910000
50%	0.700000	61.800000	57.000000	2401.000000	5.700000	5.710000	3.530000
75%	1.040000	62.500000	59.000000	5324.000000	6.540000	6.540000	4.040000
max	5.010000	79.000000	95.000000	18823.000000	10.740000	58.900000	31.800000

	carat	cut	color	clarity	depth	table	price	x	y	z
9677	1.52	Fair	H	I1	65.4	62.0	4648	7.10	7.02	4.62
4867	1.00	Premium	G	SI2	61.4	61.0	3713	6.35	6.32	3.89
30725	0.41	Good	D	SI1	63.2	58.0	738	4.72	4.77	3.00
26344	0.32	Ideal	G	VS1	61.8	55.0	645	4.42	4.45	2.74
3132	0.79	Ideal	D	SI1	61.3	54.0	3328	5.96	6.01	3.67
44811	0.50	Ideal	E	VS2	61.4	57.0	1624	5.08	5.11	3.13
16565	1.01	Premium	G	VS1	62.8	59.0	6618	6.37	6.34	3.99
49627	0.30	Premium	E	SI2	61.9	58.0	540	4.31	4.28	2.66
1276	0.81	Very Good	I	VS1	62.7	58.0	2950	5.90	5.96	3.72
22520	1.50	Very Good	H	VS2	61.6	55.0	10558	7.37	7.43	4.56

	carat	cut	color	clarity	depth	table	price	x	y	z
0	0.23	0	1	6	61.5	55.0	326	3.95	3.98	2.43
1	0.21	1	1	5	59.8	61.0	326	3.89	3.84	2.31
2	0.23	3	1	3	56.9	65.0	327	4.05	4.07	2.31
3	0.29	1	5	4	62.4	58.0	334	4.20	4.23	2.63
4	0.31	3	6	6	63.3	58.0	335	4.34	4.35	2.75
...	...	...	...	...	...	...	...	...	...	...
53938	0.86	1	4	6	61.0	58.0	2757	6.15	6.12	3.74
53939	0.75	0	0	6	62.2	55.0	2757	5.83	5.87	3.64
53940	0.71	1	1	5	60.5	55.0	2756	5.79	5.74	3.49
53941	0.71	1	2	5	59.8	62.0	2756	5.74	5.73	3.43
53942	0.70	2	1	4	60.5	59.0	2757	5.71	5.76	3.47

	truth	prediction	difference
0	4669	6435.994975	1766
1	8653	11322.936664	2669
2	975	1096.992393	121
3	14474	10977.923292	3496
4	716	156.402876	559
...	...	...	...
10777	1439	2934.525315	1495
10778	6040	6255.182911	215
10779	2484	2792.777654	308
10780	1053	601.646564	451
10781	4921	4669.914091	251

Diamond prices prediction¶

Introduction¶

Domain understaining¶

Research Questions¶

Domain Understanding and Impact Analysis¶

Data sourcing¶

Analytic approach¶

Data provisioning¶

Data collection¶

Data Understanding¶

Exploratory Data Analysis¶

Featuress distributions¶

Price¶

Diamond's depth¶

Diamond's table¶

Distribution of carat¶

Diamonds measurement y¶

Diamonds measurement x¶

Diamonds measurement z¶

Cut , clarity and color¶

Feature Price relashionship¶

Numerical features vs. Price (Scatter plots)¶

Categorical features vs. Price¶

Data Preparation¶

Encoding¶

Linear regression¶

Preprocessing¶

Feature selection¶

1- All features¶

Splitting into train/test¶

modelling¶

Evaluation¶

Plot the residuals¶

2- 4Cs of diamonds¶

Splitting into train/test¶

modelling¶

Evaluation¶

Plot the residuals¶

3- Dimensions z,y and x¶

Splitting into train/test¶

Modelling¶

Evaluation¶

Plot the residuals¶

4- Depth and Table Percentage¶

Plot the residuals¶

5-carat and dimensions¶

Plot the residuals¶

Random Forest¶

Random Forest Modeling with Chosen Features¶

Splitting into train/test¶

Modelling¶

Evaluation¶

Hyperparameter Tuning¶

Modelling¶

Boosting¶

Interference¶

Demostrations¶

Stakeholders¶

Stakeholder 1: Future Diamond Buyer¶

Background¶

Number of Intakes and Duration¶

First Intake¶

Model Accuracy Questioning¶

Second Intake¶

Stakeholder Comments¶

Stakeholder 2: Senegalese Jeweler¶

Background¶

Number of Intakes and Duration¶

Intake¶

Stakeholder Comments¶

Demonstration Process¶

Feedback¶

Common Feedback Themes¶

Model Value¶

Efficiency¶

Duration Analysis¶

Stakeholder 1: Future Diamond Buyer¶

Overview¶

Detailed Feedback¶

Suggestions for Improvement¶